debugging p4
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
index 488e23d..d2d3969 100644
--- a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobGen/JobGenerator.java
@@ -5,12 +5,9 @@
import java.io.IOException;
import edu.uci.ics.genomix.oldtype.PositionWritable;
-import edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat;
-import edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat;
-import edu.uci.ics.genomix.pregelix.format.LogAlgorithmForPathMergeInputFormat;
-import edu.uci.ics.genomix.pregelix.format.LogAlgorithmForPathMergeOutputFormat;
-import edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat;
-import edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanInputFormat;
+import edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat;
+import edu.uci.ics.genomix.pregelix.format.InitialGraphCleanInputFormat;
import edu.uci.ics.genomix.pregelix.io.VertexValueWritable;
import edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeAddVertex;
import edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeRemoveVertex;
@@ -28,67 +25,67 @@
public static String outputBase = "src/test/resources/jobs/";
- private static void generateNaiveAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(NaiveAlgorithmForPathMergeVertex.class);
- job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class); //DataCleanInputFormat
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(NaiveAlgorithmForPathMergeVertex.KMER_SIZE, 3);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
+// private static void generateNaiveAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(NaiveAlgorithmForPathMergeVertex.class);
+// job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class); //GraphCleanInputFormat
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(NaiveAlgorithmForPathMergeVertex.KMER_SIZE, 3);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genNaiveAlgorithmForMergeGraph() throws IOException {
+// generateNaiveAlgorithmForMergeGraphJob("NaiveAlgorithmForMergeGraph", outputBase
+// + "NaiveAlgorithmForMergeGraph.xml");
+// }
- private static void genNaiveAlgorithmForMergeGraph() throws IOException {
- generateNaiveAlgorithmForMergeGraphJob("NaiveAlgorithmForMergeGraph", outputBase
- + "NaiveAlgorithmForMergeGraph.xml");
- }
-
- private static void generateLogAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(LogAlgorithmForPathMergeVertex.class);
- job.setVertexInputFormatClass(LogAlgorithmForPathMergeInputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class); //LogAlgorithmForPathMergeOutputFormat
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(LogAlgorithmForPathMergeVertex.KMER_SIZE, 3);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genLogAlgorithmForMergeGraph() throws IOException {
- generateLogAlgorithmForMergeGraphJob("LogAlgorithmForMergeGraph", outputBase + "LogAlgorithmForMergeGraph.xml");
- }
-
- private static void generateP3ForMergeGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(P3ForPathMergeVertex.class);
- job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(P3ForPathMergeVertex.KMER_SIZE, 3);
- job.getConfiguration().setFloat(P3ForPathMergeVertex.PSEUDORATE, 0.3f);
- job.getConfiguration().setInt(P3ForPathMergeVertex.MAXROUND, 2);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genP3ForMergeGraph() throws IOException {
- generateP3ForMergeGraphJob("P3ForMergeGraph", outputBase
- + "P3ForMergeGraph.xml");
- }
+// private static void generateLogAlgorithmForMergeGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(LogAlgorithmForPathMergeVertex.class);
+// job.setVertexInputFormatClass(LogAlgorithmForPathMergeInputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class); //LogAlgorithmForPathMergeOutputFormat
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(LogAlgorithmForPathMergeVertex.KMER_SIZE, 3);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genLogAlgorithmForMergeGraph() throws IOException {
+// generateLogAlgorithmForMergeGraphJob("LogAlgorithmForMergeGraph", outputBase + "LogAlgorithmForMergeGraph.xml");
+// }
+//
+// private static void generateP3ForMergeGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(P3ForPathMergeVertex.class);
+// job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(P3ForPathMergeVertex.KMER_SIZE, 3);
+// job.getConfiguration().setFloat(P3ForPathMergeVertex.PSEUDORATE, 0.3f);
+// job.getConfiguration().setInt(P3ForPathMergeVertex.MAXROUND, 2);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genP3ForMergeGraph() throws IOException {
+// generateP3ForMergeGraphJob("P3ForMergeGraph", outputBase
+// + "P3ForMergeGraph.xml");
+// }
private static void generateP4ForMergeGraphJob(String jobName, String outputPath) throws IOException {
PregelixJob job = new PregelixJob(jobName);
job.setVertexClass(P4ForPathMergeVertex.class);
- job.setVertexInputFormatClass(DataCleanInputFormat.class); //NaiveAlgorithmForPathMergeInputFormat //
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
+ job.setVertexInputFormatClass(InitialGraphCleanInputFormat.class);
+ job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
job.setDynamicVertexValueSize(true);
job.setOutputKeyClass(PositionWritable.class);
job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(P4ForPathMergeVertex.KMER_SIZE, 5);
+ job.getConfiguration().setInt(P4ForPathMergeVertex.KMER_SIZE, 3);
job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
}
@@ -97,118 +94,118 @@
+ "P4ForMergeGraph.xml");
}
- private static void generateTipAddGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(TipAddVertex.class);
- job.setVertexInputFormatClass(DataCleanOutputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(TipAddVertex.KMER_SIZE, 3);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genTipAddGraph() throws IOException {
- generateTipAddGraphJob("TipAddGraph", outputBase
- + "TipAddGraph.xml");
- }
-
- private static void generateTipRemoveGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(TipRemoveVertex.class);
- job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genTipRemoveGraph() throws IOException {
- generateTipRemoveGraphJob("TipRemoveGraph", outputBase
- + "TipRemoveGraph.xml");
- }
-
- private static void generateBridgeAddGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(BridgeAddVertex.class);
- job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(BridgeAddVertex.KMER_SIZE, 3);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genBridgeAddGraph() throws IOException {
- generateBridgeAddGraphJob("BridgeAddGraph", outputBase
- + "BridgeAddGraph.xml");
- }
-
- private static void generateBridgeRemoveGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(BridgeRemoveVertex.class);
- job.setVertexInputFormatClass(DataCleanInputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genBridgeRemoveGraph() throws IOException {
- generateBridgeRemoveGraphJob("BridgeRemoveGraph", outputBase
- + "BridgeRemoveGraph.xml");
- }
-
- private static void generateBubbleAddGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(BubbleAddVertex.class);
- job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(BubbleAddVertex.KMER_SIZE, 3);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genBubbleAddGraph() throws IOException {
- generateBubbleAddGraphJob("BubbleAddGraph", outputBase
- + "BubbleAddGraph.xml");
- }
-
- private static void generateBubbleMergeGraphJob(String jobName, String outputPath) throws IOException {
- PregelixJob job = new PregelixJob(jobName);
- job.setVertexClass(BubbleMergeVertex.class);
- job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
- job.setVertexOutputFormatClass(DataCleanOutputFormat.class);
- job.setDynamicVertexValueSize(true);
- job.setOutputKeyClass(PositionWritable.class);
- job.setOutputValueClass(VertexValueWritable.class);
- job.getConfiguration().setInt(BubbleMergeVertex.KMER_SIZE, 5);
- job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
- }
-
- private static void genBubbleMergeGraph() throws IOException {
- generateBubbleMergeGraphJob("BubbleMergeGraph", outputBase
- + "BubbleMergeGraph.xml");
- }
+// private static void generateTipAddGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(TipAddVertex.class);
+// job.setVertexInputFormatClass(GraphCleanOutputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(TipAddVertex.KMER_SIZE, 3);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genTipAddGraph() throws IOException {
+// generateTipAddGraphJob("TipAddGraph", outputBase
+// + "TipAddGraph.xml");
+// }
+//
+// private static void generateTipRemoveGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(TipRemoveVertex.class);
+// job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genTipRemoveGraph() throws IOException {
+// generateTipRemoveGraphJob("TipRemoveGraph", outputBase
+// + "TipRemoveGraph.xml");
+// }
+//
+// private static void generateBridgeAddGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(BridgeAddVertex.class);
+// job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(BridgeAddVertex.KMER_SIZE, 3);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genBridgeAddGraph() throws IOException {
+// generateBridgeAddGraphJob("BridgeAddGraph", outputBase
+// + "BridgeAddGraph.xml");
+// }
+//
+// private static void generateBridgeRemoveGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(BridgeRemoveVertex.class);
+// job.setVertexInputFormatClass(GraphCleanInputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(TipRemoveVertex.KMER_SIZE, 5);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genBridgeRemoveGraph() throws IOException {
+// generateBridgeRemoveGraphJob("BridgeRemoveGraph", outputBase
+// + "BridgeRemoveGraph.xml");
+// }
+//
+// private static void generateBubbleAddGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(BubbleAddVertex.class);
+// job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(BubbleAddVertex.KMER_SIZE, 3);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genBubbleAddGraph() throws IOException {
+// generateBubbleAddGraphJob("BubbleAddGraph", outputBase
+// + "BubbleAddGraph.xml");
+// }
+//
+// private static void generateBubbleMergeGraphJob(String jobName, String outputPath) throws IOException {
+// PregelixJob job = new PregelixJob(jobName);
+// job.setVertexClass(BubbleMergeVertex.class);
+// job.setVertexInputFormatClass(NaiveAlgorithmForPathMergeInputFormat.class);
+// job.setVertexOutputFormatClass(GraphCleanOutputFormat.class);
+// job.setDynamicVertexValueSize(true);
+// job.setOutputKeyClass(PositionWritable.class);
+// job.setOutputValueClass(VertexValueWritable.class);
+// job.getConfiguration().setInt(BubbleMergeVertex.KMER_SIZE, 5);
+// job.getConfiguration().writeXml(new FileOutputStream(new File(outputPath)));
+// }
+//
+// private static void genBubbleMergeGraph() throws IOException {
+// generateBubbleMergeGraphJob("BubbleMergeGraph", outputBase
+// + "BubbleMergeGraph.xml");
+// }
public static void main(String[] args) throws IOException {
//genNaiveAlgorithmForMergeGraph();
//genLogAlgorithmForMergeGraph();
//genP3ForMergeGraph();
//genTipAddGraph();
- genTipRemoveGraph();
- genBridgeAddGraph();
- genBridgeRemoveGraph();
- genBubbleAddGraph();
- genBubbleMergeGraph();
+// genTipRemoveGraph();
+// genBridgeAddGraph();
+// genBridgeRemoveGraph();
+// genBubbleAddGraph();
+// genBubbleMergeGraph();
genP4ForMergeGraph();
}
diff --git a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
index 79a13b3..2e67da2 100644
--- a/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
+++ b/genomix/genomix-pregelix/src/test/java/edu/uci/ics/genomix/pregelix/JobRun/PathMergeSmallTestSuite.java
@@ -43,9 +43,9 @@
public class PathMergeSmallTestSuite extends TestSuite {
private static final Logger LOGGER = Logger.getLogger(PathMergeSmallTestSuite.class.getName());
- public static final String PreFix = "data/actual"; //"graphbuildresult";
+ public static final String PreFix = "data/PathMergeTestSet"; //"graphbuildresult";
public static final String[] TestDir = { PreFix + File.separator
- + "bubblemerge/BubbleMergeGraph/bin/small_bubble"};
+ + "8"};
//+ "tipremove/TipRemoveGraph/bin/fr_with_tip"};
//+ "graphs/pathmerge/singleread"};
//+ "bridgeadd/BridgeAddGraph/bin/tworeads"};
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml
deleted file mode 100644
index 4739d59..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeAddGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>BridgeRemoveVertex.kmerSize</name><value>3</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BridgeAddGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeAddVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml
deleted file mode 100644
index f9b801a..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BridgeRemoveGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BridgeRemoveGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bridgeremove.BridgeRemoveVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>BasicPathMergeVertex.kmerSize</name><value>5</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml
deleted file mode 100644
index 452834a..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleAddGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BubbleAddGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bubblemerge.BubbleAddVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>BubbleAddVertex.kmerSize</name><value>3</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml
deleted file mode 100644
index 605a004..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/BubbleMergeGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>BubbleMergeGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.bubblemerge.BubbleMergeVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>BubbleMergeVertex.kmerSize</name><value>5</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
index 5ef1509..f20a863 100644
--- a/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
+++ b/genomix/genomix-pregelix/src/test/resources/jobs/P4ForMergeGraph.xml
@@ -58,7 +58,7 @@
<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
+<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.oldtype.PositionWritable</value></property>
<property><name>tasktracker.http.threads</name><value>40</value></property>
<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
@@ -96,7 +96,7 @@
<property><name>io.sort.mb</name><value>100</value></property>
<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>BasicPathMergeVertex.kmerSize</name><value>5</value></property>
+<property><name>BasicPathMergeVertex.kmerSize</name><value>3</value></property>
<property><name>mapred.task.profile</name><value>false</value></property>
<property><name>job.end.retry.interval</name><value>30000</value></property>
<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
@@ -117,12 +117,12 @@
<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
<property><name>job.end.retry.attempts</name><value>0</value></property>
<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
+<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.GraphCleanOutputFormat</value></property>
<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanInputFormat</value></property>
+<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.InitialGraphCleanInputFormat</value></property>
<property><name>mapred.job.queue.name</name><value>default</value></property>
<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
<property><name>pregelix.incStateLength</name><value>true</value></property>
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml
deleted file mode 100644
index 00c857e..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/TipAddGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>TipAddVertex.kmerSize</name><value>3</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>TipAddGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.tipremove.TipAddVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file
diff --git a/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml b/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml
deleted file mode 100644
index 588cc9f..0000000
--- a/genomix/genomix-pregelix/src/test/resources/jobs/TipRemoveGraph.xml
+++ /dev/null
@@ -1,142 +0,0 @@
-<?xml version="1.0" encoding="UTF-8" standalone="no"?><configuration>
-<property><name>mapred.tasktracker.dns.nameserver</name><value>default</value></property>
-<property><name>mapred.queue.default.acl-administer-jobs</name><value>*</value></property>
-<property><name>mapred.skip.map.auto.incr.proc.count</name><value>true</value></property>
-<property><name>mapred.jobtracker.instrumentation</name><value>org.apache.hadoop.mapred.JobTrackerMetricsInst</value></property>
-<property><name>mapred.skip.reduce.auto.incr.proc.count</name><value>true</value></property>
-<property><name>fs.hsftp.impl</name><value>org.apache.hadoop.hdfs.HsftpFileSystem</value></property>
-<property><name>mapred.submit.replication</name><value>10</value></property>
-<property><name>ipc.server.tcpnodelay</name><value>false</value></property>
-<property><name>fs.checkpoint.dir</name><value>${hadoop.tmp.dir}/dfs/namesecondary</value></property>
-<property><name>mapred.output.compression.type</name><value>RECORD</value></property>
-<property><name>mapred.job.shuffle.merge.percent</name><value>0.66</value></property>
-<property><name>mapred.child.java.opts</name><value>-Xmx200m</value></property>
-<property><name>mapred.queue.default.acl-submit-job</name><value>*</value></property>
-<property><name>keep.failed.task.files</name><value>false</value></property>
-<property><name>mapred.jobtracker.job.history.block.size</name><value>3145728</value></property>
-<property><name>mapred.output.value.class</name><value>edu.uci.ics.genomix.pregelix.io.VertexValueWritable</value></property>
-<property><name>io.bytes.per.checksum</name><value>512</value></property>
-<property><name>mapred.task.tracker.report.address</name><value>127.0.0.1:0</value></property>
-<property><name>hadoop.util.hash.type</name><value>murmur</value></property>
-<property><name>fs.hdfs.impl</name><value>org.apache.hadoop.hdfs.DistributedFileSystem</value></property>
-<property><name>fs.ramfs.impl</name><value>org.apache.hadoop.fs.InMemoryFileSystem</value></property>
-<property><name>mapred.jobtracker.restart.recover</name><value>false</value></property>
-<property><name>fs.hftp.impl</name><value>org.apache.hadoop.hdfs.HftpFileSystem</value></property>
-<property><name>fs.checkpoint.period</name><value>3600</value></property>
-<property><name>mapred.child.tmp</name><value>./tmp</value></property>
-<property><name>mapred.local.dir.minspacekill</name><value>0</value></property>
-<property><name>map.sort.class</name><value>org.apache.hadoop.util.QuickSort</value></property>
-<property><name>hadoop.logfile.count</name><value>10</value></property>
-<property><name>ipc.client.connection.maxidletime</name><value>10000</value></property>
-<property><name>io.map.index.skip</name><value>0</value></property>
-<property><name>mapred.tasktracker.expiry.interval</name><value>600000</value></property>
-<property><name>mapred.output.compress</name><value>false</value></property>
-<property><name>io.seqfile.lazydecompress</name><value>true</value></property>
-<property><name>mapred.reduce.parallel.copies</name><value>5</value></property>
-<property><name>fs.checkpoint.size</name><value>67108864</value></property>
-<property><name>mapred.job.reduce.input.buffer.percent</name><value>0.0</value></property>
-<property><name>mapred.job.name</name><value>TipRemoveGraph</value></property>
-<property><name>local.cache.size</name><value>10737418240</value></property>
-<property><name>fs.s3n.impl</name><value>org.apache.hadoop.fs.s3native.NativeS3FileSystem</value></property>
-<property><name>mapred.userlog.limit.kb</name><value>0</value></property>
-<property><name>fs.file.impl</name><value>org.apache.hadoop.fs.LocalFileSystem</value></property>
-<property><name>mapred.task.tracker.http.address</name><value>0.0.0.0:50060</value></property>
-<property><name>mapred.task.timeout</name><value>600000</value></property>
-<property><name>fs.kfs.impl</name><value>org.apache.hadoop.fs.kfs.KosmosFileSystem</value></property>
-<property><name>mapred.max.tracker.blacklists</name><value>4</value></property>
-<property><name>fs.s3.buffer.dir</name><value>${hadoop.tmp.dir}/s3</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.dir</name><value>/jobtracker/jobsInfo</value></property>
-<property><name>ipc.client.kill.max</name><value>10</value></property>
-<property><name>mapred.tasktracker.instrumentation</name><value>org.apache.hadoop.mapred.TaskTrackerMetricsInst</value></property>
-<property><name>mapred.reduce.tasks.speculative.execution</name><value>true</value></property>
-<property><name>io.sort.record.percent</name><value>0.05</value></property>
-<property><name>hadoop.security.authorization</name><value>false</value></property>
-<property><name>mapred.max.tracker.failures</name><value>4</value></property>
-<property><name>mapred.jobtracker.taskScheduler</name><value>org.apache.hadoop.mapred.JobQueueTaskScheduler</value></property>
-<property><name>mapred.tasktracker.dns.interface</name><value>default</value></property>
-<property><name>mapred.map.tasks</name><value>2</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.hours</name><value>0</value></property>
-<property><name>fs.s3.sleepTimeSeconds</name><value>10</value></property>
-<property><name>fs.default.name</name><value>file:///</value></property>
-<property><name>mapred.output.key.class</name><value>edu.uci.ics.genomix.type.PositionWritable</value></property>
-<property><name>tasktracker.http.threads</name><value>40</value></property>
-<property><name>mapred.tasktracker.taskmemorymanager.monitoring-interval</name><value>5000</value></property>
-<property><name>hadoop.rpc.socket.factory.class.default</name><value>org.apache.hadoop.net.StandardSocketFactory</value></property>
-<property><name>mapred.reduce.tasks</name><value>1</value></property>
-<property><name>topology.node.switch.mapping.impl</name><value>org.apache.hadoop.net.ScriptBasedMapping</value></property>
-<property><name>pregelix.vertexClass</name><value>edu.uci.ics.genomix.pregelix.operator.tipremove.TipRemoveVertex</value></property>
-<property><name>mapred.skip.reduce.max.skip.groups</name><value>0</value></property>
-<property><name>io.file.buffer.size</name><value>4096</value></property>
-<property><name>mapred.jobtracker.maxtasks.per.job</name><value>-1</value></property>
-<property><name>mapred.tasktracker.indexcache.mb</name><value>10</value></property>
-<property><name>mapred.tasktracker.map.tasks.maximum</name><value>2</value></property>
-<property><name>fs.har.impl.disable.cache</name><value>true</value></property>
-<property><name>mapred.task.profile.maps</name><value>0-2</value></property>
-<property><name>hadoop.native.lib</name><value>true</value></property>
-<property><name>fs.s3.block.size</name><value>67108864</value></property>
-<property><name>mapred.job.reuse.jvm.num.tasks</name><value>1</value></property>
-<property><name>mapred.job.tracker.http.address</name><value>0.0.0.0:50030</value></property>
-<property><name>mapred.tasktracker.reduce.tasks.maximum</name><value>2</value></property>
-<property><name>io.compression.codecs</name><value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec</value></property>
-<property><name>mapred.job.shuffle.input.buffer.percent</name><value>0.70</value></property>
-<property><name>io.seqfile.compress.blocksize</name><value>1000000</value></property>
-<property><name>mapred.queue.names</name><value>default</value></property>
-<property><name>fs.har.impl</name><value>org.apache.hadoop.fs.HarFileSystem</value></property>
-<property><name>io.mapfile.bloom.error.rate</name><value>0.005</value></property>
-<property><name>mapred.job.tracker</name><value>local</value></property>
-<property><name>io.skip.checksum.errors</name><value>false</value></property>
-<property><name>mapred.reduce.max.attempts</name><value>4</value></property>
-<property><name>fs.s3.maxRetries</name><value>4</value></property>
-<property><name>ipc.server.listen.queue.size</name><value>128</value></property>
-<property><name>fs.trash.interval</name><value>0</value></property>
-<property><name>mapred.local.dir.minspacestart</name><value>0</value></property>
-<property><name>fs.s3.impl</name><value>org.apache.hadoop.fs.s3.S3FileSystem</value></property>
-<property><name>io.seqfile.sorter.recordlimit</name><value>1000000</value></property>
-<property><name>io.mapfile.bloom.size</name><value>1048576</value></property>
-<property><name>io.sort.mb</name><value>100</value></property>
-<property><name>mapred.local.dir</name><value>${hadoop.tmp.dir}/mapred/local</value></property>
-<property><name>io.sort.factor</name><value>10</value></property>
-<property><name>BasicPathMergeVertex.kmerSize</name><value>5</value></property>
-<property><name>mapred.task.profile</name><value>false</value></property>
-<property><name>job.end.retry.interval</name><value>30000</value></property>
-<property><name>mapred.tasktracker.procfsbasedprocesstree.sleeptime-before-sigkill</name><value>5000</value></property>
-<property><name>mapred.jobtracker.completeuserjobs.maximum</name><value>100</value></property>
-<property><name>mapred.task.profile.reduces</name><value>0-2</value></property>
-<property><name>webinterface.private.actions</name><value>false</value></property>
-<property><name>hadoop.tmp.dir</name><value>/tmp/hadoop-${user.name}</value></property>
-<property><name>mapred.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.skip.attempts.to.start.skipping</name><value>2</value></property>
-<property><name>mapred.temp.dir</name><value>${hadoop.tmp.dir}/mapred/temp</value></property>
-<property><name>mapred.merge.recordsBeforeProgress</name><value>10000</value></property>
-<property><name>mapred.map.output.compression.codec</name><value>org.apache.hadoop.io.compress.DefaultCodec</value></property>
-<property><name>mapred.compress.map.output</name><value>false</value></property>
-<property><name>io.sort.spill.percent</name><value>0.80</value></property>
-<property><name>fs.checkpoint.edits.dir</name><value>${fs.checkpoint.dir}</value></property>
-<property><name>mapred.userlog.retain.hours</name><value>24</value></property>
-<property><name>mapred.system.dir</name><value>${hadoop.tmp.dir}/mapred/system</value></property>
-<property><name>mapred.line.input.format.linespermap</name><value>1</value></property>
-<property><name>job.end.retry.attempts</name><value>0</value></property>
-<property><name>ipc.client.idlethreshold</name><value>4000</value></property>
-<property><name>pregelix.vertexOutputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.DataCleanOutputFormat</value></property>
-<property><name>mapred.reduce.copy.backoff</name><value>300</value></property>
-<property><name>mapred.map.tasks.speculative.execution</name><value>true</value></property>
-<property><name>mapred.inmem.merge.threshold</name><value>1000</value></property>
-<property><name>hadoop.logfile.size</name><value>10000000</value></property>
-<property><name>pregelix.vertexInputFormatClass</name><value>edu.uci.ics.genomix.pregelix.format.NaiveAlgorithmForPathMergeInputFormat</value></property>
-<property><name>mapred.job.queue.name</name><value>default</value></property>
-<property><name>mapred.job.tracker.persist.jobstatus.active</name><value>false</value></property>
-<property><name>pregelix.incStateLength</name><value>true</value></property>
-<property><name>mapred.reduce.slowstart.completed.maps</name><value>0.05</value></property>
-<property><name>topology.script.number.args</name><value>100</value></property>
-<property><name>mapred.skip.map.max.skip.records</name><value>0</value></property>
-<property><name>fs.ftp.impl</name><value>org.apache.hadoop.fs.ftp.FTPFileSystem</value></property>
-<property><name>mapred.task.cache.levels</name><value>2</value></property>
-<property><name>mapred.job.tracker.handler.count</name><value>10</value></property>
-<property><name>io.serializations</name><value>org.apache.hadoop.io.serializer.WritableSerialization</value></property>
-<property><name>ipc.client.connect.max.retries</name><value>10</value></property>
-<property><name>mapred.min.split.size</name><value>0</value></property>
-<property><name>mapred.map.max.attempts</name><value>4</value></property>
-<property><name>jobclient.output.filter</name><value>FAILED</value></property>
-<property><name>ipc.client.tcpnodelay</name><value>false</value></property>
-<property><name>mapred.acls.enabled</name><value>false</value></property>
-</configuration>
\ No newline at end of file